amueller

amueller

  # Standard scientific Python imports
  import pylab as pl
  import numpy as np
  from time import time
      
  # Import datasets, classifiers and performance metrics
  from sklearn import datasets, svm, pipeline
  from sklearn.kernel_approximation import (RBFSampler,
                                            Nystroem)
  from sklearn.utils import shuffle

amueller

from sklearn.grid_search import GridSearchCV
from sklearn.cross_validation import StratifiedKFold

def main():
    mnist = fetch_mldata("MNIST original")
    X_all, y_all = mnist.data/255., mnist.target
    print("scaling")
    X = X_all[:60000, :]
    y = y_all[:60000]

amueller

from github import Github


gh = Github("SECRETKEY")
rep = gh.get_repo("scikit-learn/scikit-learn")
org = gh.get_organization("scikit-learn")
org_members = list(org.get_members())
import datetime
n_commits = {}
limit = datetime.datetime(2017, 1, 1)

amueller

amueller

import cvxpy as cvx

n_students = 130
n_projects = 30
assignment = cvx.Int(rows=n_students, cols=n_projects)

import numpy as np
rng = np.random.RandomState(0)
project_preferences = rng.rand(n_students, n_projects)

amueller

import numpy as np


def km_segmentation(image, n_segments=100, ratio=50, max_iter=100):                       
    # initialize on grid:                                                                 
    height, width = image.shape[:2]                                                       
    # approximate grid size for desired n_segments                                        
    step = np.sqrt(height * width / n_segments)                                           
    grid_y, grid_x = np.mgrid[:height, :width]                                            
    means_y = grid_y[::step, ::step]

amueller

import numpy as np
from numbers import Integral

from sklearn.externals import six
from sklearn.tree.export import _color_brew, _criterion, _tree


def plot_tree(decision_tree, max_depth=None, feature_names=None,
              class_names=None, label='all', filled=False,
              leaves_parallel=False, impurity=True, node_ids=False,

amueller

"""
Benchmarks np.bincount method vs np.mean for feature agglomeration in
../sklearn/cluster/_feature_agglomeration. Use of np.bincount provides
a significant speed up if the pooling function is np.mean.

np.bincount performs better especially as the size of X and n_clusters
increase.
"""
import matplotlib.pyplot as plt
import numpy as np

amueller

import numpy as np

from IPython.parallel import Client

from sklearn.grid_search import GridSearchCV
from sklearn.cross_validation import KFold
from sklearn.svm import SVC
from sklearn import datasets
from sklearn.preprocessing import Scaler
from sklearn.utils import shuffle